Methods of sampling-based objective quality assessment for meshes
A method including receiving, at an encoder, a first original polygonal mesh and a second distorted polygonal mesh, the first original polygonal mesh being an original polygonal mesh and the second polygonal mesh being a distorted polygonal mesh; converting the first polygonal mesh and the second polygonal mesh into two or more triangle meshes by subdividing the plurality of polygon faces of each of the first polygonal mesh and the second polygonal mesh into a plurality of triangle faces; sampling a plurality of points on each of the plurality of triangle faces from both the first and the second polygonal meshes; generating at least a first sampled point cloud for one of the first or the second polygonal mesh using the sampled plurality of points; and computing a geometry and attribute distortion profile between the first and the second polygonal meshes based on at least the first sampled point cloud.
1 . A method performed by at least one processor, the method comprising:
receiving, at an encoder, a first polygonal mesh and a second polygonal mesh, the first polygonal mesh being an original polygonal mesh and the second polygonal mesh being a distorted polygonal mesh, each of the first and the second polygonal meshes comprising a plurality of polygon faces;
converting the first polygonal mesh and the second polygonal mesh into two or more triangle meshes by subdividing the plurality of polygon faces of each of the first polygonal mesh and the second polygonal mesh into a plurality of triangle faces, each triangle face corresponding to a respective triangle mesh of the two or more triangle meshes;
sampling a plurality of points on each of the plurality of triangle faces from both the first and the second polygonal meshes;
generating at least a first sampled point cloud for one of the first or the second polygonal mesh using the sampled plurality of points; and
computing a geometry and attribute distortion profile between the first and the second polygonal meshes based on at least the first sampled point cloud.
2 . The method of claim 1 , wherein the sampling the plurality of points on a respective triangle face from the plurality of triangle faces begins at an origin point and spreads along UV axes on a 2D UV plane.
3 . The method of claim 2 , wherein the origin point is selected as a center of mass of the respective triangle face from the plurality of triangle faces.
4 . The method of claim 2 , wherein the origin point is selected as one of a plurality of vertices on the respective triangle face from the plurality of triangle faces.
5 . The method of claim 2 , wherein the origin point is selected as a point on an edge of the respective triangle face from the plurality of triangle faces.
6 . The method of claim 2 , wherein a direction of a U axis is selected to be parallel to one of a plurality of edges of the respective triangle face from the plurality of triangle faces.
7 . The method of claim 1 , wherein the geometry and attribute distortion profile is based on one of either mean squared error or peak signal to noise ratio.
8 . The method of claim 1 , wherein computing the geometry and attribute distortion profile further comprises:
generating a second sampled point cloud for either the other of the first polygonal mesh or the second polygonal mesh using the sampled plurality of points; and
determining one or more characteristics of the second sampled point cloud based on the first sampled point cloud.
9 . The method of claim 8 , wherein the computing the geometry and attribute distortion profile between the first and the second polygonal meshes is further based on the determined one or more characteristics.
10 . An apparatus comprising:
at least one memory configured to store program code; and
at least one processor configured to read the program code and operate as instructed by the program code, the program code comprising:
receiving code configured to cause the at least one processor to receive, at an encoder, a first polygonal mesh and a second polygonal mesh, the first polygonal mesh being an original polygonal mesh and the second polygonal mesh being a distorted polygonal mesh, each of the first and the second polygonal meshes comprising a plurality of polygon faces;
converting code configured to cause the at least one processor to convert the first polygonal mesh and the second polygonal mesh into two or more triangle meshes by subdividing the plurality of polygon faces of each of the first polygonal mesh and the second polygonal mesh into a plurality of triangle faces, each triangle face corresponding to a respective triangle mesh of the two or more triangle meshes;
sampling code configured to cause the at least one processor to sample a plurality of points on each of the plurality of triangle faces from both the first and the second polygonal meshes;
generating code configured to cause the at least one processor to generate at least a first sampled point cloud for one of the first or the second polygonal mesh using the sampled plurality of points; and
computing code configured to cause the at least one processor to compute a geometry and attribute distortion profile between the first and the second polygonal meshes based on at least the first sampled point cloud.
11 . The apparatus according to claim 10 , wherein the sampling the plurality of points on a respective triangle face from the plurality of triangle faces begins at an origin point and spreads along UV axes on a 2D UV plane.
12 . The apparatus according to claim 11 , wherein the origin point is selected as a center of mass of the respective triangle face from the plurality of triangle faces.
13 . The apparatus according to claim 11 , wherein the origin point is selected as one of a plurality of vertices on the respective triangle face from the plurality of triangle faces.
14 . The apparatus according to claim 11 , wherein the origin point is selected as a point on an edge of the respective triangle face from the plurality of triangle faces.
15 . The apparatus according to claim 11 , wherein a direction of a U axis is selected to be parallel to one of a plurality of edges of the respective triangle face from the plurality of triangle faces.
16 . The apparatus according to claim 10 , wherein the geometry and attribute distortion profile is based on one of either mean squared error or peak signal to noise ratio.
17 . The apparatus according to claim 10 , wherein the computing code further causes the at least one processor to:
generate a second sampled point cloud for either the other of the first polygonal mesh and the second polygonal mesh using the sampled plurality of points; and
determine one or more characteristics of the second sampled point cloud based on the first sampled point cloud.
18 . The apparatus according to claim 17 , wherein the computing the geometry and attribute distortion profile between the first and the second polygonal meshes is further based on the determined one or more characteristics.
19 . A non-transitory computer-readable storage medium, storing instructions, which, when executed by at least one processor, cause the at least one processor to:
receive, at an encoder, a first polygonal mesh and a second polygonal mesh, the first polygonal mesh being an original polygonal mesh and the second polygonal mesh being a distorted polygonal mesh, each of the first and the second polygonal meshes comprising a plurality of polygon faces;
convert the first polygonal mesh and the second polygonal mesh into two or more triangle meshes by subdividing the plurality of polygon faces of each of the first polygonal mesh and the second polygonal mesh into a plurality of triangle faces, each triangle face corresponding to a respective triangle mesh of the two or more triangle meshes;
sample a plurality of points on each of the plurality of triangle faces from both the first and the second polygonal meshes;
generate at least a first sampled point cloud for one of the first or the second polygonal mesh using the sampled plurality of points; and
compute a geometry and attribute distortion profile between the and the second polygonal meshes based on at least the first sampled point cloud.
20 . The non-transitory computer-readable storage medium according to claim 19 , wherein the sampling the plurality of points on a respective triangle face from the plurality of triangle faces begins at an origin point and spreads along UV axes on a 2D UV plane.